arXiv subjects

Wei Li

Publications and source records attributed to Wei Li.

At least 109 records · Page 6Linked to original sources

arXiv2026

ALTER: Modeling Longitudinal Changes via Regional Differencing for 3D CT Report Generation

Computed tomography (CT) is widely used for clinical diagnosis and longitudinal follow-up, yet automatically generating accurate and complete radiology reports from three-dimensional (3D) CT remains challenging. Existing methods improve fine-grained correspondence between images and text by modeling anatomical regions, but remain centered on the current examination. Consequently, patient-specific longitudinal changes within individual regions remain insufficiently modeled. Meanwhile, interval changes are often distributed across multiple anatomical regions, complicating a coherent assessment of the overall longitudinal state. We propose Anatomically Localized Temporal Evidence Representation (ALTER) to address these limitations. Global Prior Integration (GPI) incorporates the prior CT and report to establish historical context for the current examination. Regional Proxy Differencing (RPD) enables each current anatomical region to retrieve a historical proxy from a single shared encoding of the prior volume and to derive localized interval evidence. Interval Change Fusion (ICF) further combines current abnormality states with region-distributed differences, converting their joint representation into change-aware soft prompts that guide report generation. ALTER achieves state-of-the-art results on most evaluation metrics across the RadGenome-ChestCT validation and CTRG-Chest-548K test sets. Code and data preprocessing details are available at https://github.com/peytonkarlie/ALTER/tree/main.

cs.CV↗

arXiv2026

GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?

Spatial intelligence is fundamental to embodied agents, yet existing benchmarks focus on local spatial perception from single or few viewpoints, overlooking global spatial awareness over continuous, long-horizon visual streams. To address this limitation, we introduce the Global-Spatial-Temporal Benchmark (GST-Bench), a VQA benchmark for global spatial intelligence in video understanding, comprising human-verified questions derived from 6,790 minutes of synthetically generated video. It requires models to perform accurate spatial inference from novel viewpoints unseen in the input video and to map egocentric observations onto global top-down images. A comprehensive evaluation of 22 state-of-the-art VLMs exposes a striking gap between models and humans: the strongest zero-shot model attains only 42.68, far below the human score of 79.08. To probe the cause of this gap, we construct GST-Bench-Local and find that models, despite strong local spatial understanding under the same task formulation, still fail to consolidate long-horizon observations into a globally consistent scene representation. We further provide GST-Train, a dataset for global spatial reasoning, as a complementary resource to facilitate future research on this challenge.

cs.CV↗

arXiv2026

IcFuzz: Fuzzing Isaac Sim with Semantic Stage Guidance and Multi-level Mutation

Robotics simulators serve as a foundational infrastructure for embodied AI, facilitating safe and scalable robotic system development. NVIDIA Isaac Sim has emerged as one of the most popular simulators, distinguished by its GPU-accelerated physics engine and photorealistic rendering, which enable high-fidelity modeling of complex environments. However, its inherent complexity inevitably introduces software bugs that can compromise simulation reliability. Existing fuzzing approaches struggle to test Isaac Sim effectively due to challenges of context-aware object semantics, hierarchical simulation control, and a vast simulation state space. In this paper, we propose IcFuzz, the first fuzzing approach for Isaac Sim. IcFuzz first performs an LLM-based semantic stage segmentation, decomposing simulation programs into structured stages that capture context-aware object semantics. Guided by this information, IcFuzz designs multi-level mutation operators to systematically exercise the simulator across hierarchical granularities. To efficiently navigate the vast simulation state space, IcFuzz employs a multi-armed bandit algorithm to adaptively schedule mutation operators. Experimental results show that IcFuzz outperforms the baselines in terms of both code coverage and bug detection. Specifically, IcFuzz achieves approximately 190\%--205\% of the code coverage of the baselines and detects an average of 3.7 unique crashes over three rounds of 12-hour tests, while no crashes are detected by the baselines. Moreover, IcFuzz has uncovered 11 bugs over approximately four months, 9 of which have been confirmed or fixed by the developers.

cs.RO↗

arXiv2026

Improved covariant analysis of $B_c^+ \to χ_{c1}(nP)$ decays and implications for the nature of $χ_{c1}(3872)$

We study the weak decays $B_c^+\toχ_{c1}(nP)\ell^+ ν_{\ell}$ and $B_c^+\toχ_{c1}(nP)X$ (n=1,2,3) within the Bethe-Salpeter formalism, treating $χ_{c1}(3872)$ as the conventional $χ_{c1}(2P)$ charmonium. We upgrade the covariant hadronic transition amplitude to consistently evaluate the final-state wave function in its rest frame, enabling a reliable description of large-recoil processes and sizable relativistic corrections pertinent to highly excited charmonium. Our results provide a novel platform to probe the internal structure of $χ_{c1}(3872)$ via $B_c$ decays. While the LHCb search for $B_c^+\toχ_{c1}(3872)π^+$ yielded only an upper limit, we demonstrate that this is primarily due to insufficient luminosity, approximately 20 times the current $B_c$ data sample would be required for a definitive observation. In contrast, we identify the semileptonic mode $B_c^+\toχ_{c1}(3872)μ^+ν_μ$ as a far more promising channel, which could become accessible with merely twice the existing data set. Our predictions offer concrete guidance for upcoming LHCb analyses and complement ongoing efforts to resolve the nature of $χ_{c1}(3872)$.

hep-ph↗

arXiv2026

When Shared Rollouts Fail in Defensive Driving Evaluation: A NAVSIM Score Basis Audit

Defensive driving scores are useful only when they preserve distinctions between policies that observe surrounding actors and those that do not. Re-simulation benchmarks may use reference-conditioned forgiveness, under which an agent receives credit when the logged human reference fails a compliance channel. When agent and reference share an unstable rollout transformation, this rule can propagate shared reference failures into broad compliance credit. We audit this risk in NAVSIM v2.2 original scene single-stage scoring. Under the affected documented-stack condition on the audited numerical backend, the route-blind Ignore-All probe and a route-aware actor-blind probe outrank human replay and PDM-Closed over the complete 12,146-token navtest split. A fresh installation following the public specification reproduces rollout divergence on a fixed 32-token diagnostic set. A same-source dependency stack control and an exact-input diagnostic isolate dependency-sensitive numerical behavior in the shared velocity refit. On a 450-token control pool, replacing only the solver eliminates rollout divergence and restores blind-last ordering while keeping forgiveness enabled. Thus, the numerical instability is the direct trigger. Reference-conditioned forgiveness propagates the resulting shared reference failures into compliance credit. We contribute an audit protocol requiring score basis and stack disclosure, blind probes, overwrite reporting, and rollout stability tests before using such scores for defensive driving claims.

cs.AI↗

arXiv2026

MVP-Tac: A Miniaturized Dual-Modal Vision and Photoelastic Tactile Sensor for Robot-Assisted Minimally Invasive Surgery

Robot-assisted minimally invasive surgery (RMIS) offers major benefits over open and conventional laparoscopic procedures, yet it still lacks tactile feedback for palpation while operating under strict requirements to preserve reliable vision for navigation and safety. In practice, visual feedback is indispensable, and tactile solutions that cannot coexist with vision are difficult to translate into RMIS tools. To address both needs, we introduce MVP-Tac, a compact, vision-based tactile sensor that provides co-located vision and tactile sensing. MVP-Tac uses reflective photoelastic imaging: a thin photoelastic elastomer produces stress-dependent interferograms under contact that are captured by an embedded camera through a miniaturized reflective polariscope. A semi-transparent membrane and controllable illumination enable switching between visual mode and tactile mode, enabling tactile perception without sacrificing vision. We validate MVP-Tac through force calibration in the 0 to 2 N range and demonstrate its potential for tumor palpation via video-based hardness classification on tissue phantoms, achieving 97% accuracy for exposed-tumor classification and 92% accuracy for subdermal-tumor classification. Finally, we conduct a simulated colonoscopy to validate both visual and tactile modalities in a constrained lumen, including vision-guided 3D photomapping of the luminal wall and in situ hardness classification of localized nodules. Overall, MVP-Tac provides a practical path toward restoring clinically useful palpation in RMIS while maintaining essential visual feedback. The design, fabrication, and firmware of MVP-Tac are open-sourced at https://mvp-tac.github.io/

cs.RO↗

arXiv2026

Sample-half-inserted quantum interferometer

Quantum technologies have been widely recognized as unprecedented opportunities for ultra-high precision metrology. As a celebrated example in modern quantum optics, the Hong-Ou-Mandel (HOM) interferometer is well-known for enabling temporal resolutions on the attosecond scale. However, the relatively low Fisher information per trial in ordinary HOM measurements typically necessitates tens of thousands of repetitions to achieve such precision. Here, we propose and demonstrate a sample-half-inserted HOM (SHOM) interferometer, which enhances the Fisher information by five orders of magnitude in a single interference event. By introducing an asymmetric photon-sample interaction, the SHOM configuration produces a distinctive dip-bump-dip interference structure, converting what was previously viewed as an artifact into a helpful metrological resource. Experimentally, we measured the optical path difference with an average precision of 4.09 nm (13.63 as) and an average accuracy of 1.22 nm (4.07 as) using $O(10^7)$ photons. Our results establish SHOM interferometry as an efficient phase-insensitive approach, not only paving the way toward practical quantum-enhanced thickness measurement for transparent materials, but also serving as an elegant strategy to improve the performance of various quantum devices.

quant-ph↗

arXiv2026

Descending into the Modular Bootstrap

In this paper, we attempt to explore the landscape of two-dimensional conformal field theories (2d CFTs) by efficiently searching for numerical solutions to the modular bootstrap equation using machine-learning-style optimization. The torus partition function of a 2d CFT is fixed by the spectrum of its primary operators and its chiral algebra, which we take to be the Virasoro algebra with $c>1$. We translate the requirement that this partition function is modular invariant into a loss function, which we then minimize to identify possible primary spectra. Our approach involves two technical innovations that facilitate finding reliable candidate CFTs. The first is a strategy to estimate the uncertainty associated with truncating the spectrum to the lowest dimension operators. The second is the use of a new singular-value-based optimizer (Sven) that is more effective than gradient descent at navigating the hierarchical structure of the loss landscape. We numerically construct candidate truncated CFT partition functions with central charges between 1 and $\frac{8}{7}$, a range devoid of known examples, and argue that these candidates likely come from a continuous space of modular bootstrap solutions. We also provide evidence for a more stringent constraint on the spectral gap near $c = 1$ than the existing bound of $Δ_{\rm gap} \le \frac{c}{6} + \frac{1}{3}$.

hep-th↗

arXiv2026

Harnessing Adversarial Distillation to Customise Debiased, Disease-Specific Pathology Foundation Models for Breast Cancer

Pathology foundation models (PFMs) provide strong tissue representations and have become central to digital pathology. However, deployment in disease-specific settings is limited by 1) the high computational cost of billion-parameter PFMs and 2) distribution mismatch and non-biological bias inherited from pan-cancer, multi-centre pre-training, including site-specific signatures and imbalanced disease prevalence. These factors can encourage shortcut learning and under-emphasise subtle morphology required for reliable modelling of a specific cancer type. We present SmartStu (a Smart Student), a framework to customise compact, breast-cancer-specific PFMs via distillation whilst mitigating confounding. SmartStu distils representations from multiple teacher PFMs into a lightweight student backbone. Crucially, we introduce adversarial distillation that leverages a dedicated noise model trained to predict nuisance, edge-dominated cues on the distillation set. Using this noise model as a counterexample, the adversarial objective encourages the student to recognise, yet suppress, features predictive of nuisance targets. We further incorporate multi-teacher ensemble distillation and an auxiliary self-supervised objective with artefact injection. We validate SmartStu on three external cohorts (Yale HER2, SLN-Breast, and BRACS) with multiple tiny backbones. SmartStu yields breast-cancer-specific PFMs that are over $30\times$ smaller than general PFMs whilst largely preserving, and sometimes improving, downstream performance measured by balanced accuracy (bAcc) and AUC. Code is available at https://github.com/zwchen03/advDistall.

cs.CV↗

arXiv2026

Cellular-Communication-Level Interpretability for Pathology Foundation Models via Graph Distillation on Microenvironment

Pathology foundation models (PFMs) provide strong tile-level representations but remain difficult to interpret at the cellular and microenvironmental scales that underpin clinical reasoning. We introduce Graph-Interpreter (G-Interp), a graph-distillation framework that equips a frozen PFM teacher with a cellular-communication-level "plug-in" interpreter, without modifying the teacher. For each tile, we segment cells as graph nodes and construct a microenvironment graph based on spatial adjacency. Graph neural network (GNN) students distil the PFM embedding, whilst learning attention-based message passing that yields node- and edge-level importances. We interpret these importances as cell-cell communication evidence, providing fine-grained explanations of how PFMs encode microenvironmental context. To stabilise distillation when graph abstraction is imperfect, we employ a lightweight auxiliary student to supply complementary visual cues and condition graph message passing, while keeping the primary interpretability signal graph-derived. We evaluate explanation faithfulness by mapping graph-selected evidence back to the image using instance masks and measuring teacher sensitivity under targeted vs non-target occlusions. Across multiple histopathology tasks, G-Interp produces highly scalable, microenvironment-aware explanations, while maintaining competitive predictive performance.

cs.CV↗

arXiv2026

Dual Enhancement of Superconductivity in FeSe/SrTiO3 via Orbital and Correlation Synergy

In iron-based superconductors, the dz2 orbital band typically resides far below the Fermi level and has not been considered to participate in Cooper pairing. Here, using monolayer FeSe/SrTiO3 as a model system, we demonstrate that tip-induced tensile strain controllably shifts the dz2 band toward the Fermi level, driving a two-stage enhancement of superconductivity. In-plane lattice expansion first enhances electronic correlation, amplifying superconductivity in the initial stage. As strain further increases, the upward-shifted dz2 band hybridizes with the dxy band, reconstructing the pairing-active d-orbital bands and inducing a secondary, stronger gap enhancement. Collectively, these two stages enlarge the superconducting gap from 17.8 to 23.6 meV. Throughout this process, invariant Fermi wave vectors confirm that the enhancement originates from band renormalization and reconstruction rather than carrier doping. Our work establishes a route to tailor superconducting states via strain-activated electronic correlations and band engineering, and reveals a previously unrecognized orbital-selective pairing mechanism with broad implications for correlated multiband superconductors.

cond-mat.supr-con↗

arXiv2026

Fostering cultural change in research through innovative knowledge sharing, evaluation, and community engagement strategies

Bringing together researchers, funders, industry partners, and publishers from 14 countries across 5 continents, we advance the debate around open-science, assessment and learning. We introduce an integrative "open knowledge system" framework linking knowledge production, validation, assessment, and reuse into one ecosystem view, and translate it into actionable recommendations for each stakeholder. Shifting focus to modular, machine-readable knowledge objects, these recommendations are intended to help diagnose misaligned incentives and guide reforms that properly value all scientific contributions.

cs.SI↗

arXiv2026

ANDES, the high-resolution spectrograph for the ELT: design and performance analysis of the YJH spectrograph

The ArmazoNes high Dispersion Echelle Spectrograph (ANDES) is a powerful second-generation high-resolution spectroscopic instrument for the Extremely Large Telescope (ELT). The UBV, RIZ, and YJH modules comprise fibre-fed spectrographs of the ANDES baseline design and will offer continuous wavelength coverage of 0.35-1.8 $μ$m, with the addition of a K-band channel providing coverage up to 2.4 $μ$m. Coupled with a spectral resolution of $\sim$100,000, ANDES must deliver the required wavelength calibration stability of 1 m/s over 24 hours, with a goal of 0.02 m/s across 10 years. These requirements establish the framework for the infrared module of ANDES, the YJH Spectrograph, leading to what will likely be the largest cryogenic, ultra-stable, high-resolution spectrograph ever built, and will offer the unique ability to observe in both seeing- and diffraction-limited modes interchangeably. We present the current design and performance analysis of the ANDES YJH Spectrograph, outlining the engineering challenges encountered alongside the corresponding strategies adopted to navigate them. In particular, we detail the technology development of the primary dispersing element, an echelle grating mosaic that will span over a metre in length.

astro-ph.IM↗

arXiv2026

Modulating task outcome value to mitigate real-world procrastination via noninvasive brain stimulation

Procrastination represents one of the most prevalent behavioral problems associated with individual health and societal productivity. Despite its high prevalence and substantial impact on daily functioning, its underlying neurocognitive mechanisms remain poorly understood. A leading model posits that procrastination arises from imbalanced competing motivations: the avoidance of negative task aversiveness and the pursuit of positive task outcomes, yet this framework has not been fully validated in real-world settings and not applied effectively to guide interventions. Here, we addressed this gap with a double-blind, randomized controlled trial. We applied seven sessions of high-definition transcranial direct current stimulation (HD-tDCS) to the left dorsolateral prefrontal cortex (DLPFC) in chronic procrastinators. Using the intensive experience sampling method (iESM), we assessed the effect of anodal HD-tDCS on real-world procrastination at offline after-effect (2-day interval) and long-term after-effect (6-month follow-up). We found that this neuromodulation produced a lasting reduction in real-world procrastination, with effects sustained at a 6-month follow-up. While the intervention is significantly associated with both decreased task aversiveness and increased perceived task outcome value, a mediation analysis indicated a disassociable mechanism: the increase in task outcome value (but not task aversiveness) showed a statistical pattern consistent with accounting for the observed behavioral improvement. In conclusion, the findings are consistent with the hypothesis that enhancing DLPFC function may reduce procrastination by selectively amplifying the valuation of future rewards, not by simply reducing negative feelings about the task. These results align with established decision-theoretic frameworks and suggest a targeted, theory-informed avenue for future behavioral interventions.

q-bio.NC↗

arXiv2026

Realizing Scaling Laws in Recommender Systems: A Foundation-Expert Paradigm for Hyperscale Model Deployment

Scaling laws have been established for recommender systems, yet efficiently deploying foundation model (FM) across multiple recommendation surfaces remains a major unsolved challenge. Existing methods for transfer learning face fundamental limitations in this setting: knowledge distillation suffers from transfer fidelity degradation in the large-data regime, and static user or item embeddings lack the expressiveness to capture contextualized user-item interactions. We propose the Foundation-Expert paradigm, where a central FM generates target-aware embeddings which are ingested by lightweight surface-specific expert models. Target-aware embeddings are representations that dynamically capture a user's interest in a specific item conditioned on their full interaction history. Unlike knowledge distillation, which transfers FM knowledge as soft labels, our approach provides these embeddings as input features to each expert model, enabling direct interaction with surface-specific representations. This paradigm achieves transfer ratios of 0.64--1.0 from FM to experts, substantially exceeding existing methods. Fully deployed at Meta serving tens of billions of daily requests since 2025, it delivers 0.050% statistically significant online topline metric improvement and 0.359% cumulative gains across multiple surfaces.

cs.IR↗

arXiv2026

Revisiting Degree-Corrected Spectral Clustering: a Condition-Free Spectral Analysis and Extension

Spectral clustering is a representative graph clustering technique with strong interpretability and theoretical guarantees. Degree-corrected spectral clustering (DCSC) has emerged as the state-of-the-art for this technique. While prior studies have provided impressive theoretical insights for DCSC, their analyses typically depend on specific probabilistic frameworks (e.g., stochastic block models) and conditions. In this study, we explore an alternative condition-free analysis for the clustering quality of DCSC from a pure spectral view, without any random graph models. It gives bounds for the number of mis-clustered nodes w.r.t. the optimal partition of conductance minimization while involving quantities that indicate impacts of (\romannumeral1) degree heterogeneity and (\romannumeral2) weakness of clustering structures to the clustering quality. Inspired by graph neural networks (GNNs) and their over-smoothing effect, we propose ASCENT (Adaptive Spectral ClustEring with Node-wise correcTion), a simple yet effective extension of DCSC. Different from most DCSC methods with a constant degree correction, ASCENT follows a node-wise correction scheme. It can assign different corrections for nodes via a GNN mean aggregator. We demonstrate that (\romannumeral1) ASCENT reduces to conventional DCSC methods when encountering over-smoothing; (\romannumeral2) some early stages before over-smoothing can potentially result in better clustering quality.

cs.SI↗

arXiv2026

Quasi-Non-Hermitian Edge Bursts Induced by Nonuniform Loss

Non-Hermitian quantum walks on lossy lattices with open boundaries can exhibit an anomalous peak of the loss probability at the boundary, known as the non-Hermitian edge burst (NHEB). This phenomenon has been attributed to the combined effect of the non-Hermitian skin effect (NHSE) and a gapless imaginary spectrum. Here we investigate a class of models in which the NHSE is induced by magnetic flux while the loss is spatially nonuniform. We show that the spatial distribution of loss plays a crucial role in determining the emergence and strength of the NHEB. Notably, even in the absence of the NHSE, a weak boundary accumulation of the loss probability persists. We term this effect a quasi-non-Hermitian edge burst (quasi-NHEB). By analyzing the dependence of the loss probability on the initial position, we further demonstrate that the quasi-NHEB obeys a bulk-edge scaling relation distinct from that of conventional NHEB. Our results show that spatially nonuniform loss alone can generate boundary-localized loss anomalies even without the NHSE, providing new insight into non-Hermitian boundary phenomena and a broader platform for their exploration and potential applications.

quant-ph↗

arXiv2026

Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation

Reverse Chain-of-Thought Generation (RCG) synthesizes reasoning traces from query-answer pairs, but answer-visible generation can justify a pre-committed answer rather than derive it. This post-hoc rationalization creates a train-inference mismatch because student models are trained on answer-conditioned traces but must reason without answer access at inference time. We quantify this mismatch through lexical, trajectory, and probabilistic anchoring, measuring surface overlap, answer-conditioned generation dynamics, and answer recoverability from the trace, respectively. We find that semantic suppression, a seemingly intuitive mitigation, reduces lexical overlap but increases trajectory anchoring: avoiding the answer requires continually tracking it, thereby strengthening its influence on generation. We therefore propose Structural Skeleton-guided Reasoning (SSR), which replaces suppression with structural decoupling by first generating an abstract functional skeleton and then using it to guide the full reasoning trace. Anchoring analyses show that SSR reduces all three forms of answer dependence. Across in-domain and out-of-distribution benchmarks, its distilled variant, SSR-D, improves performance by up to 10 points over suppression baselines and better preserves out-of-distribution performance. Code is available at https://github.com/viniferagy/SSR.

cs.CL↗